Downloading Model Separately

app.py

@@ -7,6 +7,12 @@ from usellm import Message, Options, UseLLM
 from transformers import AutoTokenizer, AutoModelForCausalLM
 from transformers import WhisperProcessor, WhisperForConditionalGeneration
 
+processor1 = WhisperProcessor.from_pretrained("openai/whisper-large-v2")
+model1 = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large-v2")
+
+tokenizer1 = AutoTokenizer.from_pretrained("microsoft/BioGPT-Large-PubMedQA", add_special_tokens=False)
+model = AutoModelForCausalLM.from_pretrained("microsoft/BioGPT-Large-PubMedQA")#.to('cuda:0')
+
 
 def text_to_speech(text_input):
     CHUNK_SIZE = 1024